Abstract
Although sparse multinomial logistic regression (SMLR) has provided a useful tool for sparse classification, it suffers from inefficacy in dealing with high dimensional features and manually set initial regressor values. This has significantly constrained its applications for hyperspectral image (HSI) classification. In order to tackle these two drawbacks, an extreme sparse multinomial logistic regression (ESMLR) is proposed for effective classification of HSI. First, the HSI dataset is projected to a new feature space with randomly generated weight and bias. Second, an optimization model is established by the Lagrange multiplier method and the dual principle to automatically determine a good initial regressor for SMLR via minimizing the training error and the regressor value. Furthermore, the extended multi-attribute profiles (EMAPs) are utilized for extracting both the spectral and spatial features. A combinational linear multiple features learning (MFL) method is proposed to further enhance the features extracted by ESMLR and EMAPs. Finally, the logistic regression via the variable splitting and the augmented Lagrangian (LORSAL) is adopted in the proposed framework for reducing the computational time. Experiments are conducted on two well-known HSI datasets, namely the Indian Pines dataset and the Pavia University dataset, which have shown the fast and robust performance of the proposed ESMLR framework.
Highlights
The rich spectral information available in a hyperspectral image (HSI) allows classifying among spectrally similar materials [1], supervised classification of HSI remains a challenging task, mainly due to the fact that unfavorable ratio between the limited number of training samples and the large number of spectral band [2]
Many approaches have been proposed for dimensionality reduction and feature extraction [11,12], which include the principal component analysis (PCA) and its variations [13,14,15,16], the extended multi-attribute profiles [17,18] (EMAPs), the singular spectrum analysis (SSA) [19,20,21,22] and the segmented auto-encoder [12,22]
The linear combination of the multiple features learning (MFL) that integrates the spectral and spatial information of HSI extracted by EMAPs followed by LORSAL is employed to the extreme sparse multinomial logistic regression (ESMLR) for fast and robust data classification of HSI
Summary
The rich spectral information available in a hyperspectral image (HSI) allows classifying among spectrally similar materials [1], supervised classification of HSI remains a challenging task, mainly due to the fact that unfavorable ratio between the limited number of training samples and the large number of spectral band [2]. A linear combination of the MFL which just utilizes the linear features of the HSI is proposed for the ESMLR This operation can improve the classification results and maintain the fast speed of the ESMLR. The problem of the SMLR that uses the initial data of the HSI for performing the classification is addressed by randomly generating the input weights and bias of the input data, which will maintain the fast processing speed and improve the classification results of the HSI. The linear combination of the MFL that integrates the spectral and spatial information of HSI extracted by EMAPs followed by LORSAL is employed to the ESMLR for fast and robust data classification of HSI.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
